gradient descent

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model ICLR 2025 CompAct: Compressed Activations for Memory-Efficient LLM Training NAACL 2025 ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks ICLR 2025 Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification ICLR 2025 Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning ICML 2025 Corpus Poisoning via Approximate Greedy Gradient Descent ACL 2025 Debiased Active Learning with Variational Gradient Rectifier AAAI 2025 Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees ICLR 2025 Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer ICML 2025 Deep Random Features for Scalable Interpolation of Spatiotemporal Data ICLR 2025 DiffIM: Differentiable Influence Minimization with Surrogate Modeling and Continuous Relaxation AAAI 2025 DRM Revisited: A Complete Error Analysis JMLR 2025 DUTir at SemEval-2025 Task 4: Optimized Fine-Tuning of Linear Layers for Balanced Knowledge Forgetting and Retention SemEval 2025 Early Alignment in Two-Layer Networks Training is a Two-Edged Sword JMLR 2025 EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback JMLR 2025 Efficient Differentiable Approximation of Generalized Low-rank Regularization IJCAI 2025 Ensembles of Low-Rank Expert Adapters ICLR 2025 FastJSMA: Accelerating Jacobian-based Saliency Map Attacks through Gradient Decoupling ICCV 2025 Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks ICLR 2025 Federated Unlearning with Gradient Descent and Conflict Mitigation AAAI 2025 Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks ICLR 2025 From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes AAAI 2025 Generalisation under gradient descent via deterministic PAC-Bayes ALT 2025 General Loss Functions Lead to (Approximate) Interpolation in High Dimensions JMLR 2025 Get rid of your constraints and reparametrize: A study in NNLS and implicit bias AISTATS 2025